update-agent-harness

update-agent-harness is a skill for Claude Code, Codex from microsoft/BC-Bench. It costs 58 tokens per session (745 once invoked), scanned A, original, MIT.

A maintenance workflow for the agent programs used by BC-Bench, a benchmark for comparing coding agents.

In plain words
What is it for?
It is for reviewing release notes, updating GitHub Copilot CLI or Claude Code versions, checking compatibility, selecting useful models, and preparing a release handoff.
Why use it?
It helps update agent versions and model choices while checking whether changes could affect benchmark results.

Skill for Claude CodeCodex

About the project

BC-Bench is a benchmark for measuring coding agents on real-world Microsoft Business Central development tasks written in AL. It helps compare models and agent configurations using reproducible evaluation data.

microsoft/BC-Bench · 56 stars · on GitHub

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/microsoft/bc-bench/update-agent-harness
Any agent
npx skills add microsoft/BC-Bench --skill update-agent-harness
Clone the repo
git clone --depth 1 https://github.com/microsoft/BC-Bench

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for update-agent-harness

README.md
[![agentmods](https://agentmods.dev/badge/skills/microsoft/bc-bench/update-agent-harness.svg)](https://agentmods.dev/skills/microsoft/bc-bench/update-agent-harness)
Your own site
<a href="https://agentmods.dev/skills/microsoft/bc-bench/update-agent-harness"><img src="https://agentmods.dev/badge/skills/microsoft/bc-bench/update-agent-harness.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 745 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00058 $0.00745
Opus 5 $0.00029 $0.00373
Sonnet 5 $0.00012 $0.00149
Haiku 4.5 $0.00006 $0.00075

Measured 5d ago against content hash b6a8586c25f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

update-agent-harness scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.github/skills/update-agent-harness/SKILL.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update Agent Harness

Treat harness updates as benchmark changes. Work manually; do not create workflows, branches, pull requests, tags, or releases unless explicitly asked.

Workflow

  1. Scope: Check git status, identify the current pin in .github/actions/install-agent-harnesses/action.yml, and search for all version, model, and default references. Use the latest stable GitHub release unless the user names another version.
  2. Research: Read every intervening first-party GitHub release note. Assume the selected stable release is available on npm; do not gate the update on npm publication metadata or change the installation method. Compare changes against BC-Bench's flags, authentication, prompt mode, exit behavior, sandboxing, MCP/LSP/hooks/plugins, output parsing, debug logs, and model IDs. Resolve required compatibility changes before bumping the pin.
  3. Curate models: Availability is only a candidate signal. Include models that add a frontier baseline, distinct provider/family, useful cost or speed tier, stable successor, or specific experiment. Exclude superseded, redundant, preview/unstable, unverified, or low-value models. Prefer one representative per role.
  4. Edit: Change only the version in the existing workflow/action npm install command; do not change how the harness is installed. Update required compatibility code, synchronize curated models across the Python Literal, workflow choices, command defaults, and judge configuration, then search for stale references. Harness or model changes normally require a minor version bump in pyproject.toml; follow CONTRIBUTING.md for exceptions.
  5. Validate and report: Verify the installed version and flags, run focused harness tests and uv run pre-commit run --all-files, and run the full suite when compatibility code changed. A test evaluation using the evaluation identity is required before a full run; hand it off when credentials or infrastructure are unavailable. Report version changes, model decisions, release-note impacts, checks run, and remaining risks.

Read the full file on GitHub · 40 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 40 lines · 58 tokens per session scan A b6a8586c25f9

Subscribe to this mod's changes

update-agent-harness is a skill published in the GitHub repository microsoft/BC-Bench (56 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 745 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens